Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3377 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0253. Min Range: -6.0253
Max Act: 6.0253. Min Act: -0.1700
Data Index: 8596400 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.9003. Min Act: -0.1700
Data Index: 1726488 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.9003. Min Act: -0.1700
Data Index: 4583922 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.8691. Min Act: -0.1700
Data Index: 5146268 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.7753. Min Act: -0.1700
Data Index: 8114762 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.8066. Min Act: -0.1700
Data Index: 6982669 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.8066. Min Act: -0.1700
Data Index: 2449182 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.8066. Min Act: -0.1700
Data Index: 3415828 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.8066. Min Act: -0.1700
Data Index: 5630015 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.7441. Min Act: -0.1700
Data Index: 5542428 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.7753. Min Act: -0.1700
Data Index: 5878845 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.7128. Min Act: -0.1700
Data Index: 584049 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.7753. Min Act: -0.1700
Data Index: 2508212 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.7128. Min Act: -0.1700
Data Index: 5886813 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.6816. Min Act: -0.1700
Data Index: 1345167 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.6816. Min Act: -0.1700
Data Index: 620800 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.6816. Min Act: -0.1700
Data Index: 3991708 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.6191. Min Act: -0.1700
Data Index: 1603737 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.6503. Min Act: -0.1700
Data Index: 5358508 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.6503. Min Act: -0.1700
Data Index: 4671568 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19